ah good catch, thank you. it's also old email vs matt@plushcap.com

??

So refreshing to see this footnote in a world of slop grenades @fullstackpython 😊

😄 gotta call it out when you put the work in

you guys are cookin 🔥

💯. Though IDE is more evolving than dead? Growing into state management, and I could see visualization for code execution as a big future differentiator for IDEs over TUIs. Also, MCP is everywhere and every company is launching features that rely on MCP even if its not seen as a hot trend by the X pundits. Data from across 500+ devtools companies on MCP: plushcap.com/trends/monthly/…

Can’t wait to use Astra+DaVinci MCP to edit my next video. Feels like this could be the next step up since transcript-based editing became possible. Nice writeup @chefbrent

@AskVenice 👋 hey folks your sitemap.xml is pointing to localhost:3000 for all URLs: venice.ai/sitemap.xml

Wing Commander 😎 great pick

Nemesis system was actually AI. Checkmate Mister Zitron 🥲

Didn’t expect my F1 & AI interests to collide but 2026 battery regulations are forcing it! Here’s a fantastic explanation of narrow AI used for engine management by @eddstrawF1 that I just had to call it out as a correct way to articulate the topic: piped.video/j0_Rb84XKgA?si=9yXR…

Recursive Self-Improvement (RSI) for software harnesses is having a moment this week with @PrimeIntellect’s self-improving Prime Agent and @sawyerhood’s great article on bb, and IDE that builds itself. Here are several more of the top articles I’ve been reading to learn about RSI for harnesses in particular: * lilianweng.github.io/posts/2… - Harness Eng for Self-Improvement is just a great in-depth article about harness design patterns, not tied to any specific implementation * metr.org/blog/2025-02-14-mea… METR’s measuring automated kernel engineering from early 2025 contains a lot of detail based on 4o-level models and shows how difficult it is to measure realistic tasks which are likely necessary for RSI’s feedback loops * normaltech.ai/p/ai-agents-ca… - not about harnesses specifically but a summary on a recent paper that covers what I’ve recently realized where agents are deciding based on data, and when the data isn’t available it’s a path not taken. Perhaps a “research harness” could course correct an AI model at the right time? Links to the articles I mentioned in the intro sentence: Prime Intellect’s article on Prime Agent: primeintellect.ai/blog/prime… Sawyer’s article on bb: nitter.net/sawyerhood/status/2085… Image is from the Harness Engineering for Self-Improvement Post.

Loop engineering developer trends are now available in Plushcap. This trend tracks product features and content by dev tools companies for designing self-sustaining feedback loops around AI coding agents so they can re-prompt themselves, evaluate their own output, and iterate toward a goal without requiring a human to intervene at each step. "Ralph loops" and "Ralph Wiggum loops" are also included in this one, but not graph engineering, as that seems to be a closely related but still separate architectural branch for making AI coding tools more autonomous. Insights on loop engineering: plushcap.com/blog/loop-engin… Direct trend data link: plushcap.com/trends/monthly/… All of the data and insights are available as inputs to Claude/ChatGPT/etc via the Plushcap MCP server and API: mcp.plushcap.com

nice one @aprildagonese! what do you think of K3 vs Opus or GPT class models? Hype is real?

A few resources on local model coding agents (especially @googlegemma 4) that I'm really enjoying learning from recently: * simonpcouch.com/blog/2026-04… - 14-24B dense local models scored 0/10 on his refactoring eval but Gemma 4 26B-A4B jumped to 9/10. 26B parameters but MoE 4B active per token, so it's very fast. Matches my own experience on my 4090 RTX! * magazine.sebastianraschka.co… A great guide for wiring up local models to coding harnesses such as Claude Code, and goes into differences in models. For example, gemma4:e2b fails 0/5 on tool-reasoning tasks while Qwen 35B-A3B class solves 4-5/5 * patloeber.com/gemma-4-pi-age… - awesome walkthrough by @patlober that shows how to configure @pidotdev (which is also my local model coding harness of choice) with Gemma 4 * interconnects.ai/p/gemma-4-a… - argues that 30B parameter count is the number that matters (I disagree, 26B w/ MoE seems to be the floor for me) while 7B is for tinkering but overall a great read There seems to be a parameter floor in the ~26B model range below which local models just don't feel like as much of a breakthrough, and above that the best models like Gemma 4 and Qwen 3.x remind of of that "aha!" moment I had with Opus 4.5 early last year.

Gemma is fantastic! One of my favorite open weighted models to run and its great across so many hardware variations from 4090 RTX to mac etc 🙏

Thank you!

🙏 looking forward to seeing everyone later this week!

damn that’s an impressive subscribers trajectory: plushcap.com/companies/opena…

respect! really well done